Runway Vision Landing Validation Using Sequential Image Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aircraft systems face challenges in accurately determining and validating a safe landing location on a runway, particularly when relying on existing sensors and systems that may provide unreliable or malfunctioning information.
Innovation Solution
A vision-based landing system using cameras mounted on the aircraft to capture images of the runway, processing these images to identify common features and determine changes in their locations, and predicting a landing location based on these changes, with the option to abort landing if the predicted location is incorrect.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing sensors and systems are used to determine landing location, then the system is simpler to implement, but the reliability of landing validation deteriorates due to unreliable or malfunctioning information
Solution Approach 1:
The patent introduces an intermediary validation system that includes a camera to capture images of the runway, a processor to identify common features between sequential images, and a validation module to determine whether the aircraft is on a safe landing path. This intermediary vision-based system mediates between the pilot and the runway, providing an additional layer of validation that does not rely on potentially malfunctioning existing sensors.
Solution Approach 2:
The patent replaces reliance on traditional mechanical and electronic sensors (which may fail) with a vision-based system using cameras and image processing. The camera captures optical information of the runway environment, and the processor analyzes visual features to determine landing safety, substituting the failed mechanical sensing system with an optical-based alternative.
2Measurement precision
If vision-based image processing is implemented to verify landing location, then the accuracy of landing validation is improved, but the device complexity increases due to additional cameras and processing requirements
Solution Approach 1:
The patent creates a visual copy of the runway environment by capturing images with a camera. The processor then identifies common features between sequential images to create a processed representation of the aircraft's movement relative to the runway. This visual copying and analysis provides accurate landing location verification without requiring direct physical measurement instruments.
Solution Approach 2:
The vision-based system serves multiple functions: it captures the runway environment, tracks aircraft movement relative to runway features, validates landing location accuracy, and provides abort recommendations. This multi-functional approach consolidates several validation tasks into a single integrated system, offsetting the added complexity with operational versatility.
3Reliability
If real-time image processing is performed to detect common features and determine landing path, then the reliability of landing validation is improved, but the use of energy increases due to continuous processing requirements
Solution Approach 1:
The patent implements periodic image capture and processing during the landing approach phase. Rather than continuous processing, the system captures sequential images at discrete intervals and processes them to identify common features and determine aircraft movement. This periodic operation reduces energy consumption compared to continuous processing while maintaining reliable validation through regular updates of the landing path assessment.
Data Source
AI summary
A system includes one or more cameras configured to attach to an aircraft and capture a plurality of images. The plurality of images includes a first image including a runway and a subsequently captured second image including the runway. The system includes an aircraft computing system configured to identify common features in the first and second images, determine changes in locations of the common features between the first and second images, and determine a predicted landing location of the aircraft in the second image based on the changes in locations of the common features. The aircraft computing system is configured to abort landing on the runway based on the predicted landing location relative to the runway.